文献速递胸部介入CT

双能CT预测非小细胞肺癌支气管动脉化疗栓塞后早期复发:基于SHAP方法的可解释模型

Prediction of Early Recurrence After Bronchial Arterial Chemoembolization in Non-small Cell Lung Cancer Patients Using Dual-energy CT: An Interpretable Model Based on SHAP Methodology.
PubMed 文献 · Acad Radiol · 2025-08-09

本研究回顾性分析196例一线治疗失败后接受支气管动脉化疗栓塞的非小细胞肺癌患者,利用双能CT动脉期虚拟单能图像和碘图构建机器学习与深度学习模型预测早期复发。基于ResNet101的深度学习模型AUC为0.791,联合Rad-score、DL-score和临床特征的混合模型表现最佳(AUC=0.798)。

要点

  • 双能CT动脉期100 keV虚拟单能图像构建的机器学习模型AUC=0.751,优于其他虚拟单能图像。
  • 基于ResNet101的深度学习模型AUC=0.791,优于ResNet50和ResNet152。
  • 联合Rad-score、DL-score和临床特征的混合模型AUC=0.798,为所有模型中最佳。

核心结论

  • 双能CT有希望预测一线治疗失败的非小细胞肺癌患者支气管动脉化疗栓塞后的早期复发,为临床治疗规划提供有价值的指导。

研究设计与样本

  • 回顾性分析温州医科大学附属第五医院2023年10月至2024年6月接受支气管动脉化疗栓塞的非小细胞肺癌患者临床和影像数据,共纳入196例(训练队列n=158,测试队列n=38);使用5个动脉期虚拟单能图像(40、70、100、120、150 keV)构建逻辑回归机器学习模型,使用ResNet50/101/152架构结合碘图构建深度学习模型,并建立整合最佳Rad-score、DL-score和临床特征的联合模型;通过受试者工作特征曲线下面积(AUC)评估模型性能,应用SHAP框架进行可解释性分析。

诊断标准与关键数值

  • 100 keV机器学习模型AUC=0.751,优于其他虚拟单能图像。
  • 基于ResNet101方法的深度学习模型AUC=0.791,优于其他方法。
  • 联合Rad-score-100keV-A、Rad-score-100keV-V、DL-score-ResNet101-A、DL-score-ResNet101-V和临床特征的混合模型AUC=0.798,为所有模型中最佳。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: Bronchial artery chemoembolization (BACE) is a new treatment method for lung cancer. This study aimed to investigate the ability of dual-energy computed tomography (DECT) to predict early recurrence (ER) after BACE among patients with non-small cell lung cancer (NSCLC) who failed first-line therapy.

MATERIALS AND METHODS: Clinical and imaging data from NSCLC patients undergoing BACE at Wenzhou Medical University Affiliated Fifth *** Hospital (10/2023-06/2024) were retrospectively analyzed. Logistic regression (LR) machine learning models were developed using 5 arterial-phase (AP) virtual monoenergetic images (VMIs; 40, 70, 100, 120, and 150 keV), while deep learning models utilized ResNet50/101/152 architectures with iodine maps. A combined model integrating optimal Rad-score, DL-score, and clinical features was established. Model performance was assessed via area under the receiver operating characteristic curve analysis (AUC), with SHapley Additive exPlanations (SHAP) framework applied for interpretability.

RESULTS: A total of 196 patients were enrolled in this study (training cohort: n=158; testing cohort: n=38). The 100 keV machine learning model demonstrated superior performance (AUC=0.751) compared to other VMIs. The deep learning model based on the ResNet101 method (AUC=0.791) performed better than other approaches. The hybrid model combining Rad-score-100keV-A, Rad-score-100keV-V, DL-score-ResNet101-A, DL-score-ResNet101-V, and clinical features exhibited the best performance (AUC=0.798) among all models.

CONCLUSION: DECT holds promise for predicting ER after BACE among NSCLC patients who have failed first-line therapy, offering valuable guidance for clinical treatment planning.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Feng Y, Xu Y, Wang J, et al. Prediction of Early Recurrence After Bronchial Arterial Chemoembolization in Non-small Cell Lung Cancer Patients Using Dual-energy CT: An Interpretable Model Based on SHAP Methodology. Acad Radiol. 2025. PMID: 40784844. doi:10.1016/j.acra.2025.07.039

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。